修改readme

backend/app/agent/agent_service.py

@@ -10,7 +10,6 @@ import asyncio
 from ..main_graph.utils.main_graph_builder import build_react_main_graph
 from ..main_graph.tools.graph_tools import AVAILABLE_TOOLS, TOOLS_BY_NAME
 from ..main_graph.config import set_stream_writer
-from ..model_services.chat_services import get_all_chat_services, LocalVLLMChatProvider
 from ..main_graph.utils.rag_initializer import init_rag_tool
 from ..core.intent_classifier import get_intent_classifier
 from ..logger import info, warning, error
@@ -33,18 +32,10 @@ class AIAgentService:
     async def initialize(self):
         # 0. 初始化 Mem0 客户端
         from ..memory.mem0_client import Mem0Client
-        # 创建一个临时的 LLM 用于 Mem0（用第一个可用的）
-        chat_services = get_all_chat_services()
-        temp_llm = None
-        if chat_services:
-            temp_llm = list(chat_services.values())[0]
-        self.mem0_client = Mem0Client(temp_llm)
+        self.mem0_client = Mem0Client()
         
         # 1. 初始化 RAG 工具（如果需要）
-        def create_local_llm():
-            provider = LocalVLLMChatProvider()
-            return provider.get_service()
-        rag_tool = await init_rag_tool(create_local_llm)
+        rag_tool = await init_rag_tool()
         if rag_tool:
             self.tools.append(rag_tool)
             self.tools_by_name[rag_tool.name] = rag_tool

backend/app/main_graph/utils/rag_initializer.py

@@ -20,12 +20,11 @@ def is_initialized() -> bool:
     return _initialized
 
 
-async def init_rag_tool(local_llm_creator, force: bool = False):
+async def init_rag_tool(force: bool = False):
     """
-    初始化 RAG 工具（注册到模块级变量）
+    初始化 RAG 工具（注册到模块级变量，内部获取所需服务）
 
     Args:
-        local_llm_creator: 返回 LLM 实例的函数
         force: 是否强制重新初始化
 
     Returns:
@@ -39,20 +38,22 @@ async def init_rag_tool(local_llm_creator, force: bool = False):
         return _rag_tool
 
     try:
+        from app.model_services.chat_services import get_chat_service
+
         info("🔄 正在初始化 RAG 检索系统...")
         embeddings = get_embedding_service()
         retriever = create_parent_hybrid_retriever(
             collection_name="rag_documents",
             search_k=5,
-            embeddings=embeddings
+            embeddings=embeddings,
         )
-        rewrite_llm = local_llm_creator()
+        rewrite_llm = get_chat_service()
 
         rag_tool = create_rag_tool(
             retriever=retriever,
             llm=rewrite_llm,
             num_queries=3,
-            rerank_top_n=5
+            rerank_top_n=5,
         )
 
         _rag_tool = rag_tool

backend/app/memory/mem0_client.py

@@ -1,33 +1,36 @@
-from app.config import (
-    LLM_API_KEY, ZHIPUAI_API_KEY,
-    VLLM_BASE_URL, QDRANT_URL, QDRANT_COLLECTION_NAME, QDRANT_API_KEY,
-    LLAMACPP_EMBEDDING_URL, LLAMACPP_API_KEY,
-    ZHIPU_EMBEDDING_MODEL, ZHIPU_API_BASE
-)
-from ..model_services import get_embedding_service
-from app.logger import info, warning, error
-import time
 """
 Mem0 记忆层客户端封装模块
 负责 Mem0 的初始化、检索和存储
 """
 
 import asyncio
-from typing import Optional, List, Dict
+import time
+from typing import Optional, List
+
 from mem0 import AsyncMemory
 
+from app.config import (
+    LLM_API_KEY,
+    ZHIPUAI_API_KEY,
+    VLLM_BASE_URL,
+    QDRANT_URL,
+    QDRANT_COLLECTION_NAME,
+    QDRANT_API_KEY,
+    LLAMACPP_EMBEDDING_URL,
+    LLAMACPP_API_KEY,
+    ZHIPU_EMBEDDING_MODEL,
+    ZHIPU_API_BASE,
+)
+from app.logger import info, warning, error
+from app.model_services import get_embedding_service
+from app.model_services.chat_services import get_chat_service
+
 
 class Mem0Client:
     """Mem0 异步客户端封装类"""
 
-    def __init__(self, llm_instance):
-        """
-        初始化 Mem0 客户端
-
-        Args:
-            llm_instance: LangChain LLM 实例（用于事实提取）
-        """
-        self.llm = llm_instance
+    def __init__(self):
+        """初始化 Mem0 客户端（内部获取所需服务）"""
         self.mem0: Optional[AsyncMemory] = None
         self._initialized = False
 
@@ -35,7 +38,7 @@ class Mem0Client:
         """异步初始化 Mem0 客户端，并进行实际连接测试"""
         if self._initialized:
             return
-        
+
         try:
             # 获取可用的 embedding 服务并确定维度
             info("🔄 正在获取嵌入服务...")
@@ -43,14 +46,16 @@ class Mem0Client:
             test_embedding = embeddings.embed_query("test")
             embedding_dim = len(test_embedding)
             info(f"✅ 嵌入服务可用，向量维度: {embedding_dim}")
-            
-            # 构建 embedder 配置 - 改进的方法
-            # 检查本地 provider
-            from ..model_services.embedding_services import LocalLlamaCppEmbeddingProvider, ZhipuEmbeddingProvider
-            
+
+            # 构建 embedder 配置
+            from app.model_services.embedding_services import (
+                LocalLlamaCppEmbeddingProvider,
+                ZhipuEmbeddingProvider,
+            )
+
             embedder_config = None
             local_provider = LocalLlamaCppEmbeddingProvider()
-            
+
             if local_provider.is_available():
                 info("✅ 使用本地 llama.cpp 作为 mem0 embedder")
                 embedder_config = {
@@ -59,22 +64,20 @@ class Mem0Client:
                         "model": "Qwen3-Embedding-0.6B-Q8_0",
                         "api_key": LLAMACPP_API_KEY or "dummy-key",
                         "openai_base_url": LLAMACPP_EMBEDDING_URL,
-                    }
+                    },
                 }
             else:
                 # 检查智谱
                 zhipu_provider = ZhipuEmbeddingProvider()
                 if zhipu_provider.is_available():
                     info("✅ 使用智谱 API 作为 mem0 embedder")
-                    # 使用自定义 embedder 或者 openai 兼容方式
-                    # 注意：这里我们使用一个特殊的配置方法
                     embedder_config = {
                         "provider": "openai",
                         "config": {
                             "model": ZHIPU_EMBEDDING_MODEL,
                             "api_key": ZHIPUAI_API_KEY,
                             "openai_base_url": ZHIPU_API_BASE,
-                        }
+                        },
                     }
                 else:
                     # 都不可用，使用 dummy 配置并警告
@@ -83,12 +86,17 @@ class Mem0Client:
                         "provider": "openai",
                         "config": {
                             "model": "text-embedding-ada-002",
-                            "api_key": "dummy-key",
+                            "api_key": "***",
                             "openai_base_url": "http://localhost:8080/v1",
-                        }
+                        },
                     }
-            
-            # Mem0 配置 - 简化配置，先确保能启动
+
+            # 获取 LLM 服务（内部获取）
+            info("🔄 正在获取 LLM 服务...")
+            chat_llm = get_chat_service()
+            info("✅ LLM 服务获取成功")
+
+            # Mem0 配置
             info("🔄 正在构建 Mem0 配置...")
             config = {
                 "vector_store": {
@@ -98,7 +106,7 @@ class Mem0Client:
                         "api_key": QDRANT_API_KEY,
                         "collection_name": QDRANT_COLLECTION_NAME,
                         "embedding_model_dims": embedding_dim,
-                    }
+                    },
                 },
                 "llm": {
                     "provider": "openai",
@@ -108,31 +116,30 @@ class Mem0Client:
                         "openai_base_url": VLLM_BASE_URL or ZHIPU_API_BASE,
                         "temperature": 0.1,
                         "max_tokens": 2000,
-                    }
+                    },
                 },
                 "embedder": embedder_config,
-                "version": "v1.1"
+                "version": "v1.1",
             }
-            
+
             info("🔄 正在初始化 Mem0 实例...")
             self.mem0 = AsyncMemory.from_config(config)
             info("✅ Mem0 配置加载成功")
-            
+
             # 尝试进行连接测试，但失败不会阻止初始化
             try:
                 info("🔄 正在测试 Mem0 连接...")
-                # 使用短超时的测试
                 await asyncio.wait_for(
                     self.mem0.search("ping", user_id="test", limit=1),
-                    timeout=10.0
+                    timeout=10.0,
                 )
                 info("✅ Mem0 连接测试成功")
             except Exception as e:
                 warning(f"⚠️ Mem0 连接测试遇到问题（但继续使用）: {e}")
-            
+
             self._initialized = True
             info("🎉 Mem0 初始化完成")
-            
+
         except asyncio.TimeoutError:
             error("❌ Mem0 初始化超时")
             self.mem0 = None
@@ -140,11 +147,14 @@ class Mem0Client:
         except Exception as e:
             error(f"❌ Mem0 初始化失败: {e}")
             import traceback
+
             error(f"详细错误信息:\n{traceback.format_exc()}")
             self.mem0 = None
             self._initialized = False
 
-    async def search_memories(self, query: str, user_id: str, limit: int = 5) -> List[str]:
+    async def search_memories(
+        self, query: str, user_id: str, limit: int = 5
+    ) -> List[str]:
         """
         检索相关记忆
 
@@ -163,7 +173,7 @@ class Mem0Client:
         try:
             memories = await asyncio.wait_for(
                 self.mem0.search(query, user_id=user_id, limit=limit),
-                timeout=30.0
+                timeout=30.0,
             )
 
             if memories and "results" in memories:
@@ -183,17 +193,25 @@ class Mem0Client:
             return []
 
     async def add_memories(self, messages, user_id):
-      if not self.mem0:
-        return False
-      try:
-        start = time.time()
-        info(f"📝 开始 Mem0 add，消息数: {len(messages)}")
-        await asyncio.wait_for(
-            self.mem0.add(messages, user_id=user_id, metadata={"type": "conversation"}),
-            timeout=60.0
-        )
-        info(f"✅ Mem0 add 完成，耗时: {time.time() - start:.2f}s")
-        return True
-      except asyncio.TimeoutError:
-        error(f"❌ Mem0 记忆添加超时 (60s)，已等待 {time.time() - start:.2f}s")
-        return False
+        """添加记忆"""
+        if not self.mem0:
+            return False
+        try:
+            start = time.time()
+            info(f"📝 开始 Mem0 add，消息数: {len(messages)}")
+            await asyncio.wait_for(
+                self.mem0.add(
+                    messages, user_id=user_id, metadata={"type": "conversation"}
+                ),
+                timeout=60.0,
+            )
+            info(f"✅ Mem0 add 完成，耗时: {time.time() - start:.2f}s")
+            return True
+        except asyncio.TimeoutError:
+            error(
+                f"❌ Mem0 记忆添加超时 (60s)，已等待 {time.time() - start:.2f}s"
+            )
+            return False
+        except Exception as e:
+            error(f"❌ Mem0 add 失败: {e}")
+            return False

tools/test/test_graph_branches.py

@@ -31,25 +31,25 @@ TEST_CASES = [
         "query": "吕布的事迹？",
         "description": "测试快速 RAG 分支"
     },
-    # # 测试3: 需要推理的复杂问题 - 应该直接到 React 循环
-    # {
-    #     "name": "复杂推理测试",
-    #     "query": "请帮我分析：如果我有10万元，想要在一年内获得15%的收益，有哪些低风险的投资方案？",
-    #     "description": "测试 React 循环推理分支"
-    # },
+    # 测试3: 需要推理的复杂问题 - 应该直接到 React 循环
+    {
+        "name": "复杂推理测试",
+        "query": "请帮我分析：如果我有10万元，想要在一年内获得15%的收益，有哪些低风险的投资方案？",
+        "description": "测试 React 循环推理分支"
+    },
     # # 测试4: 需要工具调用的问题
     # {
     #     "name": "工具调用测试",
     #     "query": "搜索一下今天的天气怎么样",
     #     "description": "测试工具调用分支"
     # },
-    # # 测试5: 带记忆的对话
-    # {
-    #     "name": "记忆测试",
-    #     "query": "你刚才回答了我什么问题？",
-    #     "description": "测试记忆检索分支",
-    #     "thread_id": "test_memory_thread"
-    # }
+    # 测试5: 带记忆的对话
+    {
+        "name": "记忆测试",
+        "query": "你刚才回答了我什么问题？",
+        "description": "测试记忆检索分支",
+        "thread_id": "test_memory_thread"
+    }
 ]